Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conditional statements starting with "Should"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that pose questions or suggestions regarding actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.77
     Finder
    -0.68
     Bomb
    -0.65
    ãĥĻ
    -0.63
     Fra
    -0.62
    cule
    -0.62
    atile
    -0.62
     bombed
    -0.59
    ãĥŃ
    -0.59
     Trails
    -0.59
    POSITIVE LOGITS
    ered
    0.98
    ering
    0.96
    n
    0.79
    icum
    0.77
    arget
    0.75
    ĪĴ
    0.75
    uel
    0.73
    edi
    0.72
     be
    0.72
    ember
    0.70
    Act Density 0.044%

    No Known Activations